Robust Cerebellar Controller Design for FES-Cycling Control Systems

Current methods for automatic feedback control of functional electrical stimulation (FES) employ classical techniques, and require much trial-and-error calibration. Given the nonlinear and time-varying nature of the system, there is a need for more sophisticated control techniques. Cerebellar model articulation controller (CMAC) is the one that reflects most closely the behavior of the cerebellum, has shown great benefits for the control of complex nonlinear systems. This paper presents a robust proportional-integral-derivative (PID) based CMAC for FES cycling control systems. Successful on-line training and recalling process of CMAC accompanying the PID controller is developed. The advantage of the proposed method is mainly the ability to control sudden cycling velocity changes and robust tracking performance against external disturbances.

Keywords:

FES cycling , cerebellar model articulation controller , proportional-integral-derivative control , musculoskeletal model